rca_graph_add_node

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses important behaviors beyond the annotations: duplicate names raise an error rather than overwriting, node_type only classifies the node for reports/views and does not affect analysis, and the return value includes added_node, node_type, and total_nodes. This complements annotations like readOnlyHint=false and destructiveHint=false without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and well-organized: a two-sentence intro, a bulleted Args list, and a Returns line. The uniqueness constraint and replacement note are front-loaded and actionable. Some schema details like defaults and optional flags are repeated, but this does not meaningfully bloat the text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a graph mutation tool with an output schema and annotations, this description covers the action, the error case, all decision-relevant parameters, and the return shape. The only omissions are token and client_id, which are visible in the schema and not central to deciding when or how to invoke the tool. An agent can call this tool correctly without further lookup.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The Args section explains all user-meaningful parameters: graph_id, name, node_type with accepted values and default, and description/metadata marked as optional. It adds semantic nuance not fully explicit in the schema, such as 'doesn't affect analysis' for node_type and the uniqueness guarantee for name. Token and client_id are omitted but are standard authentication/namespace fields present in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with 'Add a typed node to a causal graph' — a specific verb, resource, and scope. The uniqueness constraint and node_type enumeration further clarify what the tool does, distinguishing it from siblings like rca_graph_add_edge and rca_graph_remove_node without needing to inspect their schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes replacement behavior to rca_graph_remove_node ('remove the existing one first with rca_graph_remove_node if you want to replace it'), which is clear when-not-to-use guidance. The primary use case is evident from the tool name and opening sentence, though it does not explicitly discuss alternatives like rca_graph_add_edge.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.